Match the Script, Adapt if Multilingual: Analyzing the Effect of Multilingual Pretraining on Cross-lingual Transferability

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F22%3ATNRCXZHJ" target="_blank" >RIV/00216208:11320/22:TNRCXZHJ - isvavai.cz</a>

Result on the web

<a href="https://aclanthology.org/2022.acl-long.106" target="_blank" >https://aclanthology.org/2022.acl-long.106</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.18653/v1/2022.acl-long.106" target="_blank" >10.18653/v1/2022.acl-long.106</a>

Result language

angličtina

Original language name

Match the Script, Adapt if Multilingual: Analyzing the Effect of Multilingual Pretraining on Cross-lingual Transferability

Original language description

Pretrained multilingual models enable zero-shot learning even for unseen languages, and that performance can be further improved via adaptation prior to finetuning. However, it is unclear how the number of pretraining languages influences a model's zero-shot learning for languages unseen during pretraining. To fill this gap, we ask the following research questions: (1) How does the number of pretraining languages influence zero-shot performance on unseen target languages? (2) Does the answer to that question change with model adaptation? (3) Do the findings for our first question change if the languages used for pretraining are all related? Our experiments on pretraining with related languages indicate that choosing a diverse set of languages is crucial. Without model adaptation, surprisingly, increasing the number of pretraining languages yields better results up to adding related languages, after which performance plateaus.In contrast, with model adaptation via continued pretraining, pretraining on a larger number of languages often gives further improvement, suggesting that model adaptation is crucial to exploit additional pretraining languages.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

—

Continuities

—

Publication year

2022

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

ISBN

978-1-955917-21-6

ISSN

—

e-ISSN

—

Number of pages

13

Pages from-to

1500-1512

Publisher name

Association for Computational Linguistics

Place of publication

—

Event location

Dublin, Ireland

Event date

Jan 1, 2022

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—